文件名称:SLAM
-
所属分类:
- 标签属性:
- 上传时间:2016-09-26
-
文件大小:718.62kb
-
已下载:0次
-
提 供 者:
-
相关连接:无下载说明:别用迅雷下载,失败请重下,重下不扣分!
介绍说明--下载内容来自于网络,使用问题请自行百度
本文研究了基于多传感器组合导航方法的SLAM,由于移动机器人无法通过单个传
感器得到可靠的信息,采用多传感器组合导航的方法可以很好的解决这个问题。本文用单个
CCD摄像头和里程计组合进行SLAM研究,并得到更准确的机器人位姿信息。首先用SIFT
算法对不同图像进行特征提取和匹配,得到本质矩阵,对它进行分解,可得到机器人的旋转
矩阵和平移向量(和实际相差一个比例因子)。然后,将它与里程计信息结合,得到机器人的
位姿。在此基础上,可以得到特征点在当前摄像机坐标系中的三维坐标,即创建特征地图。
实验结果表明,这种方法能很好的降低里程计的累积误差,提高定位精度。-In this paper, based on multi-sensor integrated navigation method of SLAM, since the mobile robot can not pass through a single
Sensors give reliable information, the use of multi-sensor integrated navigation method can solve this problem. In this paper, single
CCD camera and odometer combination SLAM research and get more accurate information on pose. Firstly SIFT
Different algorithms for image feature extraction and matching, to obtain essential matrix, it is decomposed to obtain the rotation of the robot
Matrix and translation vector (and the actual difference a scale factor). Then, combine it with the odometer information to give the robot
Pose. On this basis, the three-dimensional coordinates of the feature point can be obtained in the current camera coordinate system, the map feature is created.
Experimental results show that this method can reduce the cumulative error odometer, improve positioning accuracy.
感器得到可靠的信息,采用多传感器组合导航的方法可以很好的解决这个问题。本文用单个
CCD摄像头和里程计组合进行SLAM研究,并得到更准确的机器人位姿信息。首先用SIFT
算法对不同图像进行特征提取和匹配,得到本质矩阵,对它进行分解,可得到机器人的旋转
矩阵和平移向量(和实际相差一个比例因子)。然后,将它与里程计信息结合,得到机器人的
位姿。在此基础上,可以得到特征点在当前摄像机坐标系中的三维坐标,即创建特征地图。
实验结果表明,这种方法能很好的降低里程计的累积误差,提高定位精度。-In this paper, based on multi-sensor integrated navigation method of SLAM, since the mobile robot can not pass through a single
Sensors give reliable information, the use of multi-sensor integrated navigation method can solve this problem. In this paper, single
CCD camera and odometer combination SLAM research and get more accurate information on pose. Firstly SIFT
Different algorithms for image feature extraction and matching, to obtain essential matrix, it is decomposed to obtain the rotation of the robot
Matrix and translation vector (and the actual difference a scale factor). Then, combine it with the odometer information to give the robot
Pose. On this basis, the three-dimensional coordinates of the feature point can be obtained in the current camera coordinate system, the map feature is created.
Experimental results show that this method can reduce the cumulative error odometer, improve positioning accuracy.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
基于SLAM的移动机器人导航算法.doc
资料说明.txt
Readme-说明.htm
资料说明.txt
Readme-说明.htm
本网站为编程资源及源代码搜集、介绍的搜索网站,版权归原作者所有! 粤ICP备11031372号
1999-2046 搜珍网 All Rights Reserved.